Detecting clinician implicit biases in diagnoses using proximal causal inference

TL;DR

This paper introduces a causal inference method to detect the impact of clinician implicit biases on patient outcomes using large observational datasets, addressing limitations of traditional bias measurement techniques.

Contribution

It presents a novel proximal causal inference approach to identify bias effects in real-world medical data, advancing bias detection beyond controlled experiments.

Findings

Successfully applied to UK Biobank data

Revealed significant bias effects on health outcomes

Provides a new tool for bias awareness in healthcare

Abstract

Clinical decisions to treat and diagnose patients are affected by implicit biases formed by racism, ableism, sexism, and other stereotypes. These biases reflect broader systemic discrimination in healthcare and risk marginalizing already disadvantaged groups. Existing methods for measuring implicit biases require controlled randomized testing and only capture individual attitudes rather than outcomes. However, the "big-data" revolution has led to the availability of large observational medical datasets, like EHRs and biobanks, that provide the opportunity to investigate discrepancies in patient health outcomes. In this work, we propose a causal inference approach to detect the effect of clinician implicit biases on patient outcomes in large-scale medical data. Specifically, our method uses proximal mediation to disentangle pathway-specific effects of a patient's sociodemographic attribute on a clinician's diagnosis decision. We test our method on real-world data from the UK Biobank. Our work can serve as a tool that initiates conversation and brings awareness to unequal health outcomes caused by implicit biases.